ColorInsightX: A Personalized AI-Powered Mobile Assistive System for Color Vision Deficiency Using Object Detection and Daltonization

Read full text Summarise with VIRAT
Authors: Bhabani Mishra, Srinivas Patnaik, Purab Patro, Sritam Mahakuda, P.Sahil Rao
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Color vision deficiency (CVD) affects millions of people worldwide and limits their ability to distinguish between colors in daily activities such as selecting clothing and identifying objects. Although recent advances in computer vision have enabled assistive technologies for color-blind users, many existing systems lack personalization and contextual awareness. This paper presents ColorInsightX, an AI-powered mobile assistive system designed to enhance accessibility for individuals with CVD. The proposed system integrates the Farnsworth–Munsell 100 Hue Test to identify the type of color vision deficiency, a YOLO-based object detection model for real-time scene understanding, and color extraction techniques to determine dominant colors. It further applies Daltonization-based color correction to generate personalized visual outputs based on the user’s perception profile. The system is implemented using React Native for the front end and FastAPI for the back end to enable real-time object detection and color recognition via a mobile camera. Additionally, a text-to-speech module provides audio feedback describing detected objects and their colors, and a rule-based recommendation system assists users in selecting suitable clothing combinations. Compared with conventional color recognition tools, ColorInsightX provides a context-aware, personalized, and multimodal assistive solution that improves usability and independence for individuals with color vision deficiency.

Fields of Study & Subjects

Assistive Technology in Communication and Mobility Color Science and Applications Color perception and design

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN